DREQ: Document Re-Ranking Using Entity-based Query Understanding
This addresses document re-ranking for IR systems by improving entity-based query understanding, though it is incremental as it builds on existing entity-oriented models.
The paper tackled the problem of entity-oriented neural IR models overlooking varying entity influence on document relevance by introducing DREQ, a model that emphasizes query-relevant entities and attenuates less relevant ones to create a hybrid representation, resulting in outperforming state-of-the-art methods on four large-scale benchmarks.
While entity-oriented neural IR models have advanced significantly, they often overlook a key nuance: the varying degrees of influence individual entities within a document have on its overall relevance. Addressing this gap, we present DREQ, an entity-oriented dense document re-ranking model. Uniquely, we emphasize the query-relevant entities within a document's representation while simultaneously attenuating the less relevant ones, thus obtaining a query-specific entity-centric document representation. We then combine this entity-centric document representation with the text-centric representation of the document to obtain a "hybrid" representation of the document. We learn a relevance score for the document using this hybrid representation. Using four large-scale benchmarks, we show that DREQ outperforms state-of-the-art neural and non-neural re-ranking methods, highlighting the effectiveness of our entity-oriented representation approach.